CloakLLM

[CloakLLM @CloakLLM]

@zivuch https://t.co/PPOeDIvyLV

[CloakLLM @CloakLLM]

https://t.co/mXZWoua2PO

[CloakLLM @CloakLLM]

CloakLLM v0.8.0 - generate_compliance_report() ships.
One call. COMPLIANT or NON_COMPLIANT verdict. Per-article evidence rollup. JSON, Markdown, or PDF. The artifact you hand to an EU AI Act auditor.
Four versions to get here. 1,443 tests. MIT.

[CloakLLM @CloakLLM]

@vivekonai @zivuch "Two audiences, one substrate",
that's the clearest way I've heard it put. Saving that framing.

[CloakLLM @CloakLLM]

CloakLLM v0.6.5 - CVE fix + install-smoke CI.
python-dotenv 1.2.2 pinned.
Clean-environment smoke before every publish.
pip install -U cloakllm cloakllm-mcp
#OpenSource #Security #LLM

[CloakLLM @CloakLLM]

CloakLLM v0.6.4 - polish pass after the v0.6.3 security release.
12 hardening items. Timing-safe audit verification, MCP log hygiene, O(1) token map eviction, TS declarations.
OIDC publishing. Zero static credentials.
https://t.co/tkX4B8CiEv

[CloakLLM @CloakLLM]

CloakLLM v0.6.3 - security hardening release.
14 findings closed. 1,156 tests green. OIDC trusted publishing, no long-lived tokens.
The no-PII-in-logs guarantee is now significantly harder to break.
pip install cloakllm==0.6.3 npm install [email protected]

[CloakLLM @CloakLLM]

CloakLLM v0.6.2 is live.

The EU AI Act says log everything. GDPR says don't log PII. The only way both are true: PII never reaches the log.

v0.6.2 makes that structural, enforced at the schema level, not convention. Python + JS + MCP. MIT.

https://t.co/9GInw5zild

[CloakLLM @CloakLLM]

1k downloads/week on CloakLLM. The pattern: regulated enterprises are deploying
PII protection infrastructure now. Not waiting for August. Building the evidence
layer from day one.

#EUAIAct #LLMs

[CloakLLM @CloakLLM]

CloakLLM v0.5.2: Pluggable Detection Backends.
Write your own PII detection engine, plug it into the pipeline. The detection layer is now yours to extend. Both Python and JS. MIT licensed. https://t.co/9GInw5zild

[CloakLLM @CloakLLM]

@marryevan999 Claude

[CloakLLM @CloakLLM]

CloakLLM v0.5.1 is live. New: Normalized Token Standard - a formal spec for PII tokenization in LLM API calls. Any tool can implement it. Not just us. Open source. MIT licensed. https://t.co/9GInw5zild

[CloakLLM @CloakLLM]

Every company using LLMs is sending data somewhere. When AI projects stall over compliance, employees don't stop — they paste customer data into ChatGPT with zero protection. Shadow AI is already here.
https://t.co/lIoIDLO29M

[CloakLLM @CloakLLM]

CloakLLM v0.5.0: Context Risk Analysis.

"[PERSON_0], CEO of [ORG_0]" — tokenized, but one Google search from identified.

ContextAnalyzer scores re-identification risk: token density, descriptors, relationship edges.

pip install cloakllm==0.5.0
https://t.co/lIoIDLO29M

[CloakLLM @CloakLLM]

CloakLLM v0.4.0 - PII detection in 13 languages.
Hebrew, Chinese, Japanese, German, French, Spanish, Portuguese, Russian, Polish, Dutch, Korean, Hindi.
36 locale-specific patterns. JS NER via compromise.
33 security fixes. 527 tests.

@LiteLLM #opensource #pii #llm

[CloakLLM @CloakLLM]

CloakLLM v0.3.2: Ed25519 signed sanitization certificates.
Cryptographic proof that PII was removed before inference. Merkle tree batch proofs. Cross-language: sign in Python, verify in JS.

pip install cloakllm[attestation]

#opensource #pii #llm

[CloakLLM @CloakLLM]

CloakLLM v0.3.1 - we publish our PII detection accuracy.
108 labeled samples. 95%+ recall. CI-enforced. Run the benchmarks yourself.
Also: incremental streaming desanitization — zero buffering.
pip install cloakllm npm install cloakllm
#opensource #pii #llm @LiteLLM

[CloakLLM @CloakLLM]

v0.2.1 - Per-Entity Hashing

Same person across 47 requests? Same HMAC-SHA256 hash. No original PII stored.

Track entity frequency, prove handling to auditors, correlate across documents - all without seeing the data.

https://t.co/lIoIDLO29M

@OpenAI @AnthropicA

[CloakLLM @CloakLLM]

v0.2.0 - Custom PII Categories
Define domain-specific PII types. PATIENT_ID, EMPLOYEE_NUMBER, POLICY_REF - just a name and description.
CloakLLM + local Ollama catches what regex and NER miss. Data never leaves your machine.
https://t.co/lIoIDLO29M

@OpenAI @AnthropicAI @OllamaAI

[CloakLLM @CloakLLM]

This is why we built CloakLLM - the provider never sees the real data. Just tokens.

pip install cloakllm
npm install cloakllm

[Ziv Chen @zivuch]

Your LLM provider can read every customer name you send them.

Prompts transit in plaintext. Names, emails, SSNs - all in their logs.

Most teams haven't thought about what happens when that provider gets breached.

https://t.co/l6AxN4s7cN